opencv-python 疲劳驾驶检测
在别人的代码上修改得到的，源代码好像不太准确，主要的原理就是用dlib工具找到68个人脸关键点，然后计算点之间的欧氏距离，具体得看你想要实现什么功能
我主要检测眼睛上的点和嘴巴上的点，当眼睛上的某几个点之间的距离小于设置的阈值几帧后，判断为打盹，也就是疲劳驾驶，有时候人瞌睡的时候也会打哈欠，所以也检测了嘴巴的点，但没有做优化，嘴巴部分还可以更进一步优化的，不过太花时间了，就先不做了，思路知道就行，果然搞这个最后都变成了调参。
# -*- coding: utf-8 -*-
#导入工具包
from scipy.spatial import distance as dist
from collections import OrderedDict
import numpy as np
import argparse
import time
import dlib #人脸识别相关
import cv2
FACIAL_LANDMARKS_68_IDXS = OrderedDict([ #由于原生的字典是无序的，现在用这个来提供有序的地点
("mouth", (48, 68)),
("right_eyebrow", (17, 22)),
("left_eyebrow", (22, 27)),
("right_eye", (36, 42)),
("left_eye", (42, 48)),
("nose", (27, 36)),
("jaw", (0, 17))
])
# http://vision.fe.uni-lj.si/cvww2016/proceedings/papers/05.pdf
def eye_aspect_ratio(eye):
# 计算距离，竖直的
A = dist.euclidean(eye[1], eye[5])
B = dist.euclidean(eye[2], eye[4])
# 计算距离，水平的
C = dist.euclidean(eye[0], eye[3])
# ear值
ear = (A + B) / (2.0 * C)
return ear
def mouth_aspect_ration(mouth):
A=dist.euclidean(mouth[9],mouth[15])
return A
# 输入参数
'''ap = argparse.ArgumentParser()
ap.add_argument("-p", "--shape-predictor", required=True,
help="path to facial landmark predictor")
ap.add_argument("-v", "--video", type=str, default="",
help="path to input video file")
args = vars(ap.parse_args())'''
# 设置判断参数
EYE_AR_THRESH = 0.25
EYE_AR_CONSEC_FRAMES = 3
MOUTH_AR_THRESH = 115.0
MOUTH_AR_CONSEC_FRAMES = 7
# 初始化计数器
COUNTER1 = 0
TOTAL1 = 0
COUNTER2 = 0
TOTAL2 = 0
# 检测与定位工具
print("[INFO] loading facial landmark predictor...")
detector = dlib.get_frontal_face_detector()
#predictor = dlib.shape_predictor(args["shape_predictor"])
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')
# 分别取两个眼睛区域
(lStart, lEnd) = FACIAL_LANDMARKS_68_IDXS["left_eye"]
(rStart, rEnd) = FACIAL_LANDMARKS_68_IDXS["right_eye"]
(mouthStart, mouthEnd) = FACIAL_LANDMARKS_68_IDXS["mouth"]
# 读取视频
print("[INFO] starting video stream thread...")
#vs = cv2.VideoCapture(args["video"])
vs = cv2.VideoCapture(0)
#vs = FileVideoStream(args["video"]).start()
time.sleep(1.0)
def shape_to_np(shape, dtype="int"):
# 创建68*2
coords = np.zeros((shape.num_parts, 2), dtype=dtype)
# 遍历每一个关键点
# 得到坐标
for i in range(0, shape.num_parts):
coords[i] = (shape.part(i).x, shape.part(i).y)
return coords
# 遍历每一帧
while True:
# 预处理
frame = vs.read()[1]
if frame is None:
break
(h, w) = frame.shape[:2]
width=1200
r = width / float(w)
dim = (width, int(h * r))
frame = cv2.resize(frame, dim, interpolation=cv2.INTER_AREA)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# 检测人脸
rects = detector(gray, 0)
# 遍历每一个检测到的人脸
for rect in rects:
# 获取坐标
shape = predictor(gray, rect)
shape = shape_to_np(shape)
# 分别计算ear值
leftEye = shape[lStart:lEnd]
rightEye = shape[rStart:rEnd]
leftEAR = eye_aspect_ratio(leftEye)
rightEAR = eye_aspect_ratio(rightEye)
mouth = shape[mouthStart : mouthEnd]
mouthEAR=mouth_aspect_ration(mouth)
# 算一个平均的
ear = (leftEAR + rightEAR) / 2.0
# 绘制眼睛区域
leftEyeHull = cv2.convexHull(leftEye)
rightEyeHull = cv2.convexHull(rightEye)
mouthHull = cv2.convexHull(mouth)
cv2.drawContours(frame, [leftEyeHull], -1, (0, 255, 0), 1)
cv2.drawContours(frame, [rightEyeHull], -1, (0, 255, 0), 1)
cv2.drawContours(frame, [mouthHull], -1, (0, 255, 0), 1)
# 检查是否满足阈值
if ear > EYE_AR_THRESH:
COUNTER1 = 0
elif ear < EYE_AR_THRESH:
COUNTER1 += 1
if COUNTER1 >= EYE_AR_CONSEC_FRAMES:
TOTAL1 += 1
cv2.putText(frame, "Fatigue Driving ", (int(dim[0]/2),int(dim[1]/2)),\
cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 0, 255), 5)
COUNTER1 = 0
if mouthEAR < MOUTH_AR_THRESH:
COUNTER2 = 0
elif mouthEAR > MOUTH_AR_THRESH:
COUNTER2 += 1
if COUNTER2 >= MOUTH_AR_CONSEC_FRAMES:
TOTAL2 += 1
cv2.putText(frame, "Fatigue Driving ", (int(dim[0]/2),int(dim[1]/2)),\
cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 0, 255), 5)
COUNTER2 = 0
# 显示
cv2.putText(frame, "Blinks: {}".format(TOTAL1), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.putText(frame, "EAR: {:.2f}".format(ear), (300, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.imshow("Frame", frame)
key = cv2.waitKey(10) & 0xFF
if key == ord('q'):
break
vs.release()
cv2.destroyAllWindows()